arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.00336cs.CL
收藏

基于未来预测的神经机器翻译模型

Future-Prediction-Based Model for Neural Machine Translation

Peking University(北京大学)

Bingzhen Wei, Junyang Lin

摘要:

提出了一种新的神经机器翻译模型。与传统方法不同的是,我们的模型可以预测未来的文本长度和单词在每个解码时间步,使生成可以帮助与未来预测的信息。有了这些信息,模型不会在没有翻译足够内容的情况下停止生成。实验结果表明,我们的模型可以显着优于基线模型。此外,我们的分析表明,我们的模型是有效的预测的长度和未翻译的内容的单词。

英文摘要:

We propose a novel model for Neural Machine Translation (NMT). Different from the conventional method, our model can predict the future text length and words at each decoding time step so that the generation can be helped with the information from the future prediction. With such information, the model does not stop generation without having translated enough content. Experimental results demonstrate that our model can significantly outperform the baseline models. Besides, our analysis reflects that our model is effective in the prediction of the length and words of the untranslated content.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑